Date of Publication :7th June 2016
Abstract: Texts are scripts provided by the language to convey information. The main idea of this paper is to provide a means for people with vision disabilities to listen to the text of an image by converting text into speech. This process uses text-to-speech, the generation of synthesized speech from text. Image containing the text is pre-processed that prepares the text for recognition. Text recognizer needs to localize the text in image accurately. Separation of text from each other is done by segmentation. Segmentation is followed by the extraction of character, resizing them and storing them in a PDF document. Frequency speech synthesizer provides the speech by performing natural language processing and digital signal processing of the text.
Reference :